{"id":"https://openalex.org/W3109067582","doi":"https://doi.org/10.1109/tip.2021.3088605","title":"Learning to Discover Multi-Class Attentional Regions for Multi-Label Image Recognition","display_name":"Learning to Discover Multi-Class Attentional Regions for Multi-Label Image Recognition","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3109067582","doi":"https://doi.org/10.1109/tip.2021.3088605","mag":"3109067582","pmid":"https://pubmed.ncbi.nlm.nih.gov/34181541"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2021.3088605","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2021.3088605","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2007.01755","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000290451","display_name":"Bin-Bin Gao","orcid":"https://orcid.org/0000-0003-2572-8156"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin-Bin Gao","raw_affiliation_strings":["Tencent YouTu Lab, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-2572-8156","affiliations":[{"raw_affiliation_string":"Tencent YouTu Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100783219","display_name":"Hong-Yu Zhou","orcid":"https://orcid.org/0000-0002-1256-7050"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hong-Yu Zhou","raw_affiliation_strings":["The University of Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":13.0144,"has_fulltext":false,"cited_by_count":132,"citation_normalized_percentile":{"value":0.99005731,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"30","issue":null,"first_page":"5920","last_page":"5932"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9941999912261963,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8174408674240112},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6608072519302368},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5785088539123535},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.5694780945777893},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5687617659568787},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5470890998840332},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.5148517489433289},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4961429536342621},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.44658994674682617},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.4342396557331085},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.419728547334671},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.33900827169418335},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.12937897443771362}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8174408674240112},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6608072519302368},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5785088539123535},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.5694780945777893},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5687617659568787},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5470890998840332},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.5148517489433289},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4961429536342621},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.44658994674682617},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.4342396557331085},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.419728547334671},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33900827169418335},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.12937897443771362},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tip.2021.3088605","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2021.3088605","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},{"id":"pmid:34181541","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34181541","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null},{"id":"pmh:oai:arXiv.org:2007.01755","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.01755","pdf_url":"https://arxiv.org/pdf/2007.01755","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2007.01755","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.01755","pdf_url":"https://arxiv.org/pdf/2007.01755","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320316083","display_name":"Tencent","ror":"https://ror.org/00hhjss72"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":67,"referenced_works":["https://openalex.org/W7746136","https://openalex.org/W603908379","https://openalex.org/W1514535095","https://openalex.org/W1567302070","https://openalex.org/W1677182931","https://openalex.org/W1686810756","https://openalex.org/W1834627138","https://openalex.org/W1861492603","https://openalex.org/W1962468782","https://openalex.org/W1984279162","https://openalex.org/W2010181071","https://openalex.org/W2027266161","https://openalex.org/W2031489346","https://openalex.org/W2066380143","https://openalex.org/W2102605133","https://openalex.org/W2109255472","https://openalex.org/W2114315281","https://openalex.org/W2147527908","https://openalex.org/W2156303437","https://openalex.org/W2162915993","https://openalex.org/W2164996823","https://openalex.org/W2183231851","https://openalex.org/W2194775991","https://openalex.org/W2257483379","https://openalex.org/W2295107390","https://openalex.org/W2296447001","https://openalex.org/W2318862362","https://openalex.org/W2410641892","https://openalex.org/W2518918709","https://openalex.org/W2560023338","https://openalex.org/W2630837129","https://openalex.org/W2736688973","https://openalex.org/W2737725206","https://openalex.org/W2745461083","https://openalex.org/W2921251850","https://openalex.org/W2932399282","https://openalex.org/W2951527505","https://openalex.org/W2957702778","https://openalex.org/W2963052338","https://openalex.org/W2963163009","https://openalex.org/W2963300078","https://openalex.org/W2963306618","https://openalex.org/W2963676620","https://openalex.org/W2963697527","https://openalex.org/W2963745697","https://openalex.org/W2963875806","https://openalex.org/W2982112268","https://openalex.org/W3025645599","https://openalex.org/W3034472074","https://openalex.org/W3035665101","https://openalex.org/W3087020912","https://openalex.org/W3089555680","https://openalex.org/W3125882365","https://openalex.org/W3135745701","https://openalex.org/W6618372016","https://openalex.org/W6630875275","https://openalex.org/W6637373629","https://openalex.org/W6639102338","https://openalex.org/W6653248861","https://openalex.org/W6667154291","https://openalex.org/W6682137061","https://openalex.org/W6682864246","https://openalex.org/W6686251702","https://openalex.org/W6739696289","https://openalex.org/W6741440215","https://openalex.org/W6746352052","https://openalex.org/W6770630075"],"related_works":["https://openalex.org/W2953234277","https://openalex.org/W2626256601","https://openalex.org/W147410782","https://openalex.org/W2900413183","https://openalex.org/W4390975304","https://openalex.org/W3022252430","https://openalex.org/W2748667022","https://openalex.org/W3211770882","https://openalex.org/W2010629964","https://openalex.org/W2983135586"],"abstract_inverted_index":{"Multi-label":[0],"image":[1,12,51,127,141],"recognition":[2],"is":[3,154],"a":[4,22,39,73,117,136],"practical":[5],"and":[6,68,91,106,116,167],"challenging":[7],"task":[8],"compared":[9],"to":[10,45,52,56,80],"single-label":[11],"classification.":[13],"However,":[14],"previous":[15],"works":[16],"may":[17],"be":[18],"suboptimal":[19],"because":[20],"of":[21,25,84,95,150],"great":[23],"number":[24,83],"object":[26],"proposals":[27],"or":[28],"complex":[29],"attentional":[30,75,85],"region":[31,76,119],"generation":[32],"modules.":[33],"In":[34,146],"this":[35],"paper,":[36],"we":[37,71],"propose":[38,72],"simple":[40],"but":[41],"efficient":[42],"two-stream":[43],"framework":[44],"recognize":[46,108],"multi-category":[47],"objects":[48,110],"from":[49],"global":[50,67,162],"local":[53,69],"regions,":[54],"similar":[55],"how":[57],"human":[58],"beings":[59],"perceive":[60],"objects.":[61],"To":[62],"bridge":[63],"the":[64,82,93,148,151],"gap":[65],"between":[66],"streams,":[70],"multi-class":[74,109],"module":[77],"which":[78],"aims":[79],"make":[81],"regions":[86,97],"as":[87,89,98,100,161],"small":[88],"possible":[90],"keep":[92],"diversity":[94],"these":[96],"high":[99],"possible.":[101],"Our":[102],"method":[103,130,153],"can":[104],"efficiently":[105],"effectively":[107],"with":[111,135],"an":[112],"affordable":[113],"computation":[114],"cost":[115],"parameter-free":[118],"localization":[120],"module.":[121],"Over":[122],"three":[123],"benchmarks":[124],"on":[125],"multi-label":[126],"classification,":[128],"our":[129],"achieves":[131],"new":[132],"state-of-the-art":[133],"results":[134],"single":[137],"model":[138],"only":[139],"using":[140],"semantics":[142],"without":[143],"label":[144],"dependency.":[145],"addition,":[147],"effectiveness":[149],"proposed":[152],"extensively":[155],"demonstrated":[156],"under":[157],"different":[158],"factors":[159],"such":[160],"pooling":[163],"strategy,":[164],"input":[165],"size":[166],"network":[168],"architecture.":[169],"Code":[170],"has":[171],"been":[172],"made":[173],"available":[174],"at":[175],"https://github.com/gaobb/MCAR.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":25},{"year":2024,"cited_by_count":39},{"year":2023,"cited_by_count":37},{"year":2022,"cited_by_count":20},{"year":2021,"cited_by_count":4}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}